Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2608 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1286475 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1657. Min Act: -0.0001

Data Index: 446150 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1544. Min Act: -0.0000

Data Index: 449529 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1442. Min Act: -0.0000

Data Index: 74052 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1439. Min Act: -0.0000

Data Index: 328017 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1442. Min Act: -0.0001

Data Index: 201118 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1417. Min Act: -0.0000

Data Index: 518702 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1348. Min Act: -0.0000

Data Index: 520867 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1373. Min Act: -0.0000

Data Index: 817373 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1330. Min Act: -0.0000

Data Index: 447873 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1314330 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1373. Min Act: -0.0000

Data Index: 817634 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1277. Min Act: -0.0001

Data Index: 905376 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1352. Min Act: -0.0000

Data Index: 350021 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1324. Min Act: -0.0000

Data Index: 544017 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1119779 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1425784 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1363. Min Act: -0.0000

Data Index: 984705 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1307. Min Act: -0.0000

Data Index: 107130 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1755. Min Range: -0.1755

Max Act: 0.1159. Min Act: -0.0001

Data Index: 851122 (C4 (Web Text))

Max Activating Token Index: 431